Generative adversarial networks (GANs) have recently become a hot research topic;
however, they have been studied since 2014, and a large number of algorithms have been …

Speaker identity is one of the important characteristics of human speech. In voice
conversion, we change the speaker identity from one to another, while kee** the linguistic …

Despite the progress in voice conversion, many-to-many voice conversion trained on non-
parallel data, as well as zero-shot voice conversion, remains under-explored. Deep style …

This paper proposes a method that allows non-parallel many-to-many voice conversion (VC)
by using a variant of a generative adversarial network (GAN) called StarGAN. Our method …

In this paper, we first provide a review of the state-of-the-art emotional voice conversion
research, and the existing emotional speech databases. We then motivate the development …

Non-parallel voice conversion (VC) is a technique for learning the map** from source to
target speech without relying on parallel data. This is an important task, but it has been …

We propose a non-parallel voice-conversion (VC) method that can learn a map** from
source to target speech without relying on parallel data. The proposed method is particularly …

One-shot voice conversion (VC), which performs conversion across arbitrary speakers with
only a single target-speaker utterance for reference, can be effectively achieved by speech …

Recently, voice conversion (VC) without parallel data has been successfully adapted to multi-
target scenario in which a single model is trained to convert the input voice to many different …

Speech information can be roughly decomposed into four components: language content,
timbre, pitch, and rhythm. Obtaining disentangled representations of these components is …